diff --git a/toolbox/MMDetection/patch/mmdetection/_base_/datasets/coco_detection.py b/toolbox/MMDetection/patch/mmdetection/_base_/datasets/coco_detection.py
new file mode 100644
index 0000000000000000000000000000000000000000..fdf8dfad9476b1d7b7a4e8c3e2832f115a1ea7f2
--- /dev/null
+++ b/toolbox/MMDetection/patch/mmdetection/_base_/datasets/coco_detection.py
@@ -0,0 +1,95 @@
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+
+# Example to use different file client
+# Method 1: simply set the data root and let the file I/O module
+# automatically infer from prefix (not support LMDB and Memcache yet)
+
+# data_root = 's3://openmmlab/datasets/detection/coco/'
+
+# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
+# backend_args = dict(
+#     backend='petrel',
+#     path_mapping=dict({
+#         './data/': 's3://openmmlab/datasets/detection/',
+#         'data/': 's3://openmmlab/datasets/detection/'
+#     }))
+backend_args = None
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='PackDetInputs')
+]
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=backend_args),
+    dict(type='Resize', scale=(1333, 800), keep_ratio=True),
+    # If you don't have a gt annotation, delete the pipeline
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+train_dataloader = dict(
+    batch_size=2,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(type='DefaultSampler', shuffle=True),
+    batch_sampler=dict(type='AspectRatioBatchSampler'),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_train2017.json',
+        data_prefix=dict(img='train2017/'),
+        filter_cfg=dict(filter_empty_gt=True, min_size=32),
+        pipeline=train_pipeline,
+        backend_args=backend_args))
+val_dataloader = dict(
+    batch_size=1,
+    num_workers=2,
+    persistent_workers=True,
+    drop_last=False,
+    sampler=dict(type='DefaultSampler', shuffle=False),
+    dataset=dict(
+        type=dataset_type,
+        data_root=data_root,
+        ann_file='annotations/instances_val2017.json',
+        data_prefix=dict(img='val2017/'),
+        test_mode=True,
+        pipeline=test_pipeline,
+        backend_args=backend_args))
+test_dataloader = val_dataloader
+
+val_evaluator = dict(
+    type='CocoMetric',
+    ann_file=data_root + 'annotations/instances_val2017.json',
+    metric='bbox',
+    format_only=False,
+    backend_args=backend_args)
+test_evaluator = val_evaluator
+
+# inference on test dataset and
+# format the output results for submission.
+# test_dataloader = dict(
+#     batch_size=1,
+#     num_workers=2,
+#     persistent_workers=True,
+#     drop_last=False,
+#     sampler=dict(type='DefaultSampler', shuffle=False),
+#     dataset=dict(
+#         type=dataset_type,
+#         data_root=data_root,
+#         ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#         data_prefix=dict(img='test2017/'),
+#         test_mode=True,
+#         pipeline=test_pipeline))
+# test_evaluator = dict(
+#     type='CocoMetric',
+#     metric='bbox',
+#     format_only=True,
+#     ann_file=data_root + 'annotations/image_info_test-dev2017.json',
+#     outfile_prefix='./work_dirs/coco_detection/test')
diff --git a/toolbox/MMDetection/patch/mmdetection/_base_/default_runtime.py b/toolbox/MMDetection/patch/mmdetection/_base_/default_runtime.py
new file mode 100644
index 0000000000000000000000000000000000000000..870e5614c86d7e1bbdad13d77a0db03a46ce717a
--- /dev/null
+++ b/toolbox/MMDetection/patch/mmdetection/_base_/default_runtime.py
@@ -0,0 +1,24 @@
+default_scope = 'mmdet'
+
+default_hooks = dict(
+    timer=dict(type='IterTimerHook'),
+    logger=dict(type='LoggerHook', interval=50),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    checkpoint=dict(type='CheckpointHook', interval=1),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    visualization=dict(type='DetVisualizationHook'))
+
+env_cfg = dict(
+    cudnn_benchmark=False,
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
+    dist_cfg=dict(backend='nccl'),
+)
+
+vis_backends = [dict(type='LocalVisBackend')]
+visualizer = dict(
+    type='DetLocalVisualizer', vis_backends=vis_backends, name='visualizer')
+log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
+
+log_level = 'INFO'
+load_from = None
+resume = False
diff --git a/toolbox/MMDetection/patch/mmdetection/_base_/schedules/schedule_1x.py b/toolbox/MMDetection/patch/mmdetection/_base_/schedules/schedule_1x.py
new file mode 100644
index 0000000000000000000000000000000000000000..95f30be74ff37080ba0d227d55bbd587feeaa892
--- /dev/null
+++ b/toolbox/MMDetection/patch/mmdetection/_base_/schedules/schedule_1x.py
@@ -0,0 +1,28 @@
+# training schedule for 1x
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=1)
+val_cfg = dict(type='ValLoop')
+test_cfg = dict(type='TestLoop')
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
+    dict(
+        type='MultiStepLR',
+        begin=0,
+        end=12,
+        by_epoch=True,
+        milestones=[8, 11],
+        gamma=0.1)
+]
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
+
+# Default setting for scaling LR automatically
+#   - `enable` means enable scaling LR automatically
+#       or not by default.
+#   - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
+auto_scale_lr = dict(enable=False, base_batch_size=16)
diff --git a/toolbox/MMDetection/patch/mmdetection/configs/rtmdet/rtmdet_l_8xb32-300e_coco.py b/toolbox/MMDetection/patch/mmdetection/configs/rtmdet/rtmdet_l_8xb32-300e_coco.py
new file mode 100644
index 0000000000000000000000000000000000000000..1cce4d89c84a81d7aa22197cd6dd70fe08637a35
--- /dev/null
+++ b/toolbox/MMDetection/patch/mmdetection/configs/rtmdet/rtmdet_l_8xb32-300e_coco.py
@@ -0,0 +1,179 @@
+_base_ = [
+    '../_base_/default_runtime.py', '../_base_/schedules/schedule_1x.py',
+    '../_base_/datasets/coco_detection.py', './rtmdet_tta.py'
+]
+model = dict(
+    type='RTMDet',
+    data_preprocessor=dict(
+        type='DetDataPreprocessor',
+        mean=[103.53, 116.28, 123.675],
+        std=[57.375, 57.12, 58.395],
+        bgr_to_rgb=False,
+        batch_augments=None),
+    backbone=dict(
+        type='CSPNeXt',
+        arch='P5',
+        expand_ratio=0.5,
+        deepen_factor=1,
+        widen_factor=1,
+        channel_attention=True,
+        norm_cfg=dict(type='SyncBN'),
+        act_cfg=dict(type='SiLU', inplace=True)),
+    neck=dict(
+        type='CSPNeXtPAFPN',
+        in_channels=[256, 512, 1024],
+        out_channels=256,
+        num_csp_blocks=3,
+        expand_ratio=0.5,
+        norm_cfg=dict(type='SyncBN'),
+        act_cfg=dict(type='SiLU', inplace=True)),
+    bbox_head=dict(
+        type='RTMDetSepBNHead',
+        num_classes=80,
+        in_channels=256,
+        stacked_convs=2,
+        feat_channels=256,
+        anchor_generator=dict(
+            type='MlvlPointGenerator', offset=0, strides=[8, 16, 32]),
+        bbox_coder=dict(type='DistancePointBBoxCoder'),
+        loss_cls=dict(
+            type='QualityFocalLoss',
+            use_sigmoid=True,
+            beta=2.0,
+            loss_weight=1.0),
+        loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
+        with_objectness=False,
+        exp_on_reg=True,
+        share_conv=True,
+        pred_kernel_size=1,
+        norm_cfg=dict(type='SyncBN'),
+        act_cfg=dict(type='SiLU', inplace=True)),
+    train_cfg=dict(
+        assigner=dict(type='DynamicSoftLabelAssigner', topk=13),
+        allowed_border=-1,
+        pos_weight=-1,
+        debug=False),
+    test_cfg=dict(
+        nms_pre=30000,
+        min_bbox_size=0,
+        score_thr=0.001,
+        nms=dict(type='nms', iou_threshold=0.65),
+        max_per_img=300),
+)
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='CachedMosaic', img_scale=(640, 640), pad_val=114.0),
+    dict(
+        type='RandomResize',
+        scale=(1280, 1280),
+        ratio_range=(0.1, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=(640, 640)),
+    dict(type='YOLOXHSVRandomAug'),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type='CachedMixUp',
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=20,
+        pad_val=(114, 114, 114)),
+    dict(type='PackDetInputs')
+]
+
+train_pipeline_stage2 = [
+    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='RandomResize',
+        scale=(640, 640),
+        ratio_range=(0.1, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=(640, 640)),
+    dict(type='YOLOXHSVRandomAug'),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(type='PackDetInputs')
+]
+
+test_pipeline = [
+    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
+    dict(type='Resize', scale=(640, 640), keep_ratio=True),
+    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='PackDetInputs',
+        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                   'scale_factor'))
+]
+
+train_dataloader = dict(
+    batch_size=32,
+    num_workers=10,
+    batch_sampler=None,
+    pin_memory=True,
+    dataset=dict(pipeline=train_pipeline))
+val_dataloader = dict(
+    batch_size=5, num_workers=10, dataset=dict(pipeline=test_pipeline))
+test_dataloader = val_dataloader
+
+max_epochs = 300
+stage2_num_epochs = 20
+base_lr = 0.004
+interval = 10
+
+train_cfg = dict(
+    max_epochs=max_epochs,
+    val_interval=interval,
+    dynamic_intervals=[(max_epochs - stage2_num_epochs, 1)])
+
+val_evaluator = dict(proposal_nums=(100, 1, 10))
+test_evaluator = val_evaluator
+
+# optimizer
+optim_wrapper = dict(
+    _delete_=True,
+    type='OptimWrapper',
+    optimizer=dict(type='AdamW', lr=base_lr, weight_decay=0.05),
+    paramwise_cfg=dict(
+        norm_decay_mult=0, bias_decay_mult=0, bypass_duplicate=True))
+
+# learning rate
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.0e-5,
+        by_epoch=False,
+        begin=0,
+        end=1000),
+    dict(
+        # use cosine lr from 150 to 300 epoch
+        type='CosineAnnealingLR',
+        eta_min=base_lr * 0.05,
+        begin=max_epochs // 2,
+        end=max_epochs,
+        T_max=max_epochs // 2,
+        by_epoch=True,
+        convert_to_iter_based=True),
+]
+
+# hooks
+default_hooks = dict(
+    checkpoint=dict(
+        interval=interval,
+        max_keep_ckpts=3  # only keep latest 3 checkpoints
+    ))
+custom_hooks = [
+    dict(
+        type='EMAHook',
+        ema_type='ExpMomentumEMA',
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type='PipelineSwitchHook',
+        switch_epoch=max_epochs - stage2_num_epochs,
+        switch_pipeline=train_pipeline_stage2)
+]
diff --git a/toolbox/MMDetection/patch/mmdetection/configs/rtmdet/rtmdet_s_8xb32-300e_coco.py b/toolbox/MMDetection/patch/mmdetection/configs/rtmdet/rtmdet_s_8xb32-300e_coco.py
new file mode 100644
index 0000000000000000000000000000000000000000..cbf76247b74e94735eea0dd70ce6ac9e57f4dadf
--- /dev/null
+++ b/toolbox/MMDetection/patch/mmdetection/configs/rtmdet/rtmdet_s_8xb32-300e_coco.py
@@ -0,0 +1,62 @@
+_base_ = './rtmdet_l_8xb32-300e_coco.py'
+checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-s_imagenet_600e.pth'  # noqa
+model = dict(
+    backbone=dict(
+        deepen_factor=0.33,
+        widen_factor=0.5,
+        init_cfg=dict(
+            type='Pretrained', prefix='backbone.', checkpoint=checkpoint)),
+    neck=dict(in_channels=[128, 256, 512], out_channels=128, num_csp_blocks=1),
+    bbox_head=dict(in_channels=128, feat_channels=128, exp_on_reg=False))
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(type='CachedMosaic', img_scale=(640, 640), pad_val=114.0),
+    dict(
+        type='RandomResize',
+        scale=(1280, 1280),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=(640, 640)),
+    dict(type='YOLOXHSVRandomAug'),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type='CachedMixUp',
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=20,
+        pad_val=(114, 114, 114)),
+    dict(type='PackDetInputs')
+]
+
+train_pipeline_stage2 = [
+    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='RandomResize',
+        scale=(640, 640),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=(640, 640)),
+    dict(type='YOLOXHSVRandomAug'),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(type='PackDetInputs')
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
+
+custom_hooks = [
+    dict(
+        type='EMAHook',
+        ema_type='ExpMomentumEMA',
+        momentum=0.0002,
+        update_buffers=True,
+        priority=49),
+    dict(
+        type='PipelineSwitchHook',
+        switch_epoch=280,
+        switch_pipeline=train_pipeline_stage2)
+]
diff --git a/toolbox/MMDetection/patch/mmdetection/configs/rtmdet/rtmdet_tiny_8xb32-300e_coco.py b/toolbox/MMDetection/patch/mmdetection/configs/rtmdet/rtmdet_tiny_8xb32-300e_coco.py
new file mode 100644
index 0000000000000000000000000000000000000000..a686f4a7f0c4c3bed956c2a3fa504ea8863c669d
--- /dev/null
+++ b/toolbox/MMDetection/patch/mmdetection/configs/rtmdet/rtmdet_tiny_8xb32-300e_coco.py
@@ -0,0 +1,43 @@
+_base_ = './rtmdet_s_8xb32-300e_coco.py'
+
+checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-tiny_imagenet_600e.pth'  # noqa
+
+model = dict(
+    backbone=dict(
+        deepen_factor=0.167,
+        widen_factor=0.375,
+        init_cfg=dict(
+            type='Pretrained', prefix='backbone.', checkpoint=checkpoint)),
+    neck=dict(in_channels=[96, 192, 384], out_channels=96, num_csp_blocks=1),
+    bbox_head=dict(in_channels=96, feat_channels=96, exp_on_reg=False))
+
+train_pipeline = [
+    dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
+    dict(type='LoadAnnotations', with_bbox=True),
+    dict(
+        type='CachedMosaic',
+        img_scale=(640, 640),
+        pad_val=114.0,
+        max_cached_images=20,
+        random_pop=False),
+    dict(
+        type='RandomResize',
+        scale=(1280, 1280),
+        ratio_range=(0.5, 2.0),
+        keep_ratio=True),
+    dict(type='RandomCrop', crop_size=(640, 640)),
+    dict(type='YOLOXHSVRandomAug'),
+    dict(type='RandomFlip', prob=0.5),
+    dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))),
+    dict(
+        type='CachedMixUp',
+        img_scale=(640, 640),
+        ratio_range=(1.0, 1.0),
+        max_cached_images=10,
+        random_pop=False,
+        pad_val=(114, 114, 114),
+        prob=0.5),
+    dict(type='PackDetInputs')
+]
+
+train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
diff --git a/toolbox/MMDetection/patch/mmdetection/configs/rtmdet/rtmdet_tta.py b/toolbox/MMDetection/patch/mmdetection/configs/rtmdet/rtmdet_tta.py
new file mode 100644
index 0000000000000000000000000000000000000000..6dde36de3ff06576944a351de9daf53746103f21
--- /dev/null
+++ b/toolbox/MMDetection/patch/mmdetection/configs/rtmdet/rtmdet_tta.py
@@ -0,0 +1,36 @@
+tta_model = dict(
+    type='DetTTAModel',
+    tta_cfg=dict(nms=dict(type='nms', iou_threshold=0.6), max_per_img=100))
+
+img_scales = [(640, 640), (320, 320), (960, 960)]
+tta_pipeline = [
+    dict(type='LoadImageFromFile', backend_args=None),
+    dict(
+        type='TestTimeAug',
+        transforms=[
+            [
+                dict(type='Resize', scale=s, keep_ratio=True)
+                for s in img_scales
+            ],
+            [
+                # ``RandomFlip`` must be placed before ``Pad``, otherwise
+                # bounding box coordinates after flipping cannot be
+                # recovered correctly.
+                dict(type='RandomFlip', prob=1.),
+                dict(type='RandomFlip', prob=0.)
+            ],
+            [
+                dict(
+                    type='Pad',
+                    size=(960, 960),
+                    pad_val=dict(img=(114, 114, 114))),
+            ],
+            [dict(type='LoadAnnotations', with_bbox=True)],
+            [
+                dict(
+                    type='PackDetInputs',
+                    meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
+                               'scale_factor', 'flip', 'flip_direction'))
+            ]
+        ])
+]
diff --git a/toolbox/MMDetection/prepare_mmdetection.sh b/toolbox/MMDetection/prepare_mmdetection.sh
index af0aa6164dd40c0b15fe52cb4e194865d173eae8..d94d03dd018e9b42ef5f800e9f95b29d4b2501bc 100644
--- a/toolbox/MMDetection/prepare_mmdetection.sh
+++ b/toolbox/MMDetection/prepare_mmdetection.sh
@@ -30,6 +30,7 @@ echo "=====Prepare mmdetection ${MMDET_VERSION} START====="
 
 git clone --depth 1 -b ${MMDET_VERSION} https://github.com/open-mmlab/mmdetection.git
 
+# configs/rtmdet reference from https://github.com/open-mmlab/mmdetection/tree/fe3f809a0a514189baf889aa358c498d51ee36cd/configs/rtmdet which is first added in v3.0.0rc1
 cp -r -T patch/mmdetection/ mmdetection/
 
 cd mmdetection/